RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection

TL;DR

RSDet++ introduces a point-based, anchor-free rotated object detection method with a modulated loss to improve accuracy, especially for tiny objects, achieving competitive results on challenging benchmarks.

Contribution

The paper proposes RSDet++, a novel point-based rotated object detector with a modulated rotation loss, addressing loss discontinuity and enhancing detection of small objects.

Findings

Achieves competitive results on DOTA benchmarks.

Improves accuracy for tiny objects smaller than 10 pixels.

Demonstrates effectiveness of modulated rotation loss in rotated detection.

Abstract

We classify the discontinuity of loss in both five-param and eight-param rotated object detection methods as rotation sensitivity error (RSE) which will result in performance degeneration. We introduce a novel modulated rotation loss to alleviate the problem and propose a rotation sensitivity detection network (RSDet) which is consists of an eight-param single-stage rotated object detector and the modulated rotation loss. Our proposed RSDet has several advantages: 1) it reformulates the rotated object detection problem as predicting the corners of objects while most previous methods employ a five-para-based regression method with different measurement units. 2) modulated rotation loss achieves consistent improvement on both five-param and eight-param rotated object detection methods by solving the discontinuity of loss. To further improve the accuracy of our method on objects smaller than 10 pixels, we introduce a novel RSDet++ which is consists of a point-based anchor-free rotated object detector and a modulated rotation loss. Extensive experiments demonstrate the effectiveness of both RSDet and RSDet++, which achieve competitive results on rotated object detection in the challenging benchmarks DOTA1.0, DOTA1.5, and DOTA2.0. We hope the proposed method can provide a new perspective for designing algorithms to solve rotated object detection and pay more attention to tiny objects. The codes and models are available at: https://github.com/yangxue0827/RotationDetection.